A powerful online recommendation system in Electronic Commerce (EC) must know its targeted customers well and employ effective marketing strategies. Market research is a very important way to know the customers well. For high-tech products with great variety such as computers, cellular phones, and digital cameras, customers’ knowledge level towards products may have a decisive influence on their purchase decision. While many online recommendation systems focus on utilizing data mining techniques in user profile and transaction data, this paper presents a method for recognizing customer knowledge level as a preprocess for more effective online recommendation in EC. The method consists of two Back Propagation Networks (BPN) and predicts based on customer characteristics and online navigation behaviors. A simple simulated digital camera EC store case study was conducted and the good preliminary result implies the good potential of the proposed method.
Changchien, S. Wesley and Huang, Ru-Hui, "Recognizing Customer Knowledge Level towards Products for Recommendation in Electronic Commerce" (2003). ICEB 2003 Proceedings. 74.